Urban rail transit obstacle detection based on Improved R-CNN. (15th June 2022)

• Record Type: Journal Article
• Authors: He, Deqiang; Ren, Ruochen; Li, Kai; Zou, Zhiheng; Ma, Rui; Qin, Yuliang; Yang, Weifeng
• Is Part Of: Measurement. Volume 196(2022)
• Publication Date: 2022-06-15
• Subjects: Urban rail transit -- Obstacle detection -- Improved R-CNN -- Feature extraction; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2022.111277
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: A train obstacle detection method based on the Improved R-CNN was proposed. The Improved FPN is designed to enhance the accuracy of obstacle detection. The dataset covers more scenes and adds diverse obstacle information. Abstract: Excellent active obstacle detection capability is critical to operate fully automatic trains safely and reliably. There are some problems exist in the traditional sensor-based obstacle detection approaches, such as low detection accuracy, sluggish detection speed and a limited number of obstacle types. In this work, a fast and accurate object detector termed improved R-CNN is proposed by introducing new up-sampling parallel structure and context extraction module (CEM) into the architecture of R-CNN. Furthermore, transfer learning is applied to inherit the COCO dataset's pre-training weight. The network is trained on track lines and test lines with nine types of obstacles. The data is evaluated and statistically cleansed, and the fine-tuning anchor improves the network's flexibility within the dataset. With the input size of 1330 px × 800 px, the test results show that the improved R-CNN model achieves an accuracy of 90.6% and a detection speed of 11 FPS. In comparison to other state-of-the-art detectors, the model has great performance in obstacle identification of rail track and achieves a good balance between detection speed and accuracy.